The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The feature-extraction.md module contains Bash commands (awk, tr, grep, bc) and Python snippets for text analysis. While these are standard tools for the skill's stated purpose, they represent the execution of code on local data.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to read and analyze untrusted external text files (exemplars) to build style profiles. Maliciously crafted exemplar text could attempt to inject instructions into the resulting 'Style Profile' or influence the agent's behavior during the generation phase.
Ingestion points: Read tool usage in feature-extraction.md and exemplar-reference.md to load source texts.
Boundary markers: The skill lacks explicit boundary markers or 'ignore' instructions when processing the content of exemplar files.
Capability inventory: The skill has access to Bash, Python, Write, and Edit tools, which could be leveraged if an injection is successful.
Sanitization: Analysis is performed using regex and quantitative counters, which provides a level of structural isolation, but the resulting textual descriptions (e.g., 'Voice/Tone') are directly interpolated into future generation prompts.

style-learner